arXiv:2606.03002v2 Announce Type: replace Abstract: Quantization is a standard path to deploying large language models, and quantized models are typically judged acceptable when perplexity or downstream accuracy remains close to the full-precision original. But behavioral parity need not imply feature…
arXiv:2606.06576v1 Announce Type: new Abstract: In the sciences, regression tasks often require predicting high-dimensional outputs from few training examples. Multi-output Gaussian processes excel in low-data regimes but typically struggle with high-dimensional outputs. Compress-then-predict pipelines such as PCA-GP (principal component analysis…
arXiv:2511.02748v2 Announce Type: replace-cross Abstract: We argue that sixth-generation (6G) intelligence is not fluent token prediction but the capacity to imagine and choose — to simulate future scenarios, weigh trade-offs, and act with calibrated uncertainty. We reframe open radio access…
arXiv:2606.06624v1 Announce Type: new Abstract: In the current era of deep learning and especially generative models, there is significant investment in training very large generative models. Thus far, such models have been “black boxes” that are difficult to understand in…
arXiv:2605.25638v2 Announce Type: replace-cross Abstract: Policy loss estimation remains a fundamental and long-standing challenge in reinforcement learning (RL) for diffusion language models (DLMs). We introduce Reinforcement Learning from Denoising Feedback (RLDF), a novel training paradigm that leverages feedback obtained from…
arXiv:2606.06647v1 Announce Type: new Abstract: Objective. EEG foundation models (FMs) report strong accuracy on clinical resting-state EEG. However, high accuracy under subject-disjoint cross-validation remains ambiguous: it can reflect a genuine clinical biomarker, or subject-identity features that correlate with the label.…
arXiv:2606.07399v1 Announce Type: cross Abstract: Generative models for counterfactual outcomes have great potential to support decision-making under complex interventions, but existing approaches are limited by unstable estimation, poor generalization across environments, and bias from nuisance model misspecification. We introduce ADIGen,…
arXiv:2606.06658v1 Announce Type: new Abstract: Hydrodynamic models of stochastic particle systems represented by coarse-grained stochastic partial differential equations (SPDE), such as the regularized Dean-Kawasaki (DK) equation, do not accurately capture the short-time system dynamics that is dominated by non-Markovian effects,…
arXiv:2503.03660v4 Announce Type: replace Abstract: We introduce a sequence-conditioned critic for Soft Actor-Critic (SAC) that models trajectory context with a lightweight Transformer and trains on aggregated $N$-step targets. Unlike prior approaches that (i) score state-action pairs in isolation or (ii)…
arXiv:2606.06663v1 Announce Type: new Abstract: Future AI-integrated Radio Access Networks (AI-RAN) will combine open programmability with learning-enabled xApps, rApps, and control functions that act on shared parameters and key performance indicators (KPIs). For conflict monitoring, it is not enough to…
